BoxMOT: Pluggable SOTA multi-object tracking modules modules for segmentation, object detection and pose estimation models

OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.

Visual tracking library based on PyTorch.

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

[CVPR'19 Oral] Deeper and Wider Siamese Networks for Real-Time Visual Tracking

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

Official Python toolkit for generic object tracking benchmark GOT-10k and beyond

A minimal example (SiamFC in PyTorch) showing how to train and evaluate trackers using GOT-10k toolkit.

PyTorch implementation of paper "ARTrack" and "ARTrackV2"

Implementation SiamRPN on PyTorch with GOT-10k dataset

The official implementation for the paper [ODTrack: Online Dense Temporal Token Learning for Visual Tracking].

[CVPR 2022 Oral & TPAMI 2024] MixFormer: End-to-End Tracking with Iterative Mixed Attention

[ECCV'22] The official PyTorch implementation of our ECCV 2022 paper: "AiATrack: Attention in Attention for Transformer Visual Tracking".

Target-Aware Tracking with Long-term Context Attention

(2020-2022)The PyTorch version of SiamFC，SiamRPN，DaSiamRPN, UpdateNet , SiamDW, SiamRPN++, SiamMask, SiamFC++, SiamCAR, SiamBAN, Ocean, LightTrack , TrTr, NanoTrack; Visual object tracking based on…

SeqTrackv2: Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking

[ECCV 2022] Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework